Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent

Cosimo Galeone, Anna Ettorre, Ginevra Mariani, Minsu Park +2 more

Published

Nov 13, 2026

Citations

0

Trust level

Moderate

Usefulness score

65/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 13, 2026

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
65/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

Abstract

Can you trust a finance agent you did not build? We take the reference agent shipped with the Vals Finance Agent Benchmark v2, leave it untuned, and ask four questions a leaderboard score does not answer. Is the score stable? Seven identical runs on 18 questions pass between 105 and 123 of 149 rubric criteria, and the bill varies by up to 17%. When the agent fails, who owns the fix? We classify 20 failed trajectories, from three runs of nine held-out questions, by the layer whose owner would remedy them, under a taxonomy frozen in advance: 13 belong to the agent's instructions, 3 to its tools, 4 to the model, none to its data. Can that diagnosis be trusted? Four blind readers from three model families, given only the traces, name the same fault as our LLM analyzer in 94% of cases, the rate at which they agree with one another (93%). Can a change be trusted? An optimization loop reads the traces, makes one targeted change per round and keeps it only if it clears a fixed threshold. Under a cost objective its final configuration costs 0.34x the baseline on the held-out questions (95% CI [0.22, 0.58]) at accuracy within noise. Under an accuracy objective it gains 14 points on the development questions and 1.5 on the held-out ones (CI [-5.3, +7.2]). Judged against the measured run-to-run noise, under a rule written before the test was opened, the first is a real saving and the second is not. This is a case study of one agent and nine test questions, not a general result.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Rubric Rating

Directly usable for protocol triage.

"Can you trust a finance agent you did not build?"

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Can you trust a finance agent you did not build?"

Quality Controls

missing

Not reported

No explicit QC controls found.

"Can you trust a finance agent you did not build?"

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Can you trust a finance agent you did not build?"

Reported Metrics

strong

Accuracy

Useful for evaluation criteria comparison.

"Under a cost objective its final configuration costs 0.34x the baseline on the held-out questions (95% CI [0.22, 0.58]) at accuracy within noise."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

accuracy
Human feedback details
Uses human feedback
Yes
Feedback types
Rubric Rating
Rater population
Not reported
Unit of annotation
Multi Dim Rubric
Expertise required
Medicine
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Can you trust a finance agent you did not build?

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Can you trust a finance agent you did not build?
  • We take the reference agent shipped with the Vals Finance Agent Benchmark v2, leave it untuned, and ask four questions a leaderboard score does not answer.
  • Seven identical runs on 18 questions pass between 105 and 123 of 149 rubric criteria, and the bill varies by up to 17%.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Contribution summary

  • Can you trust a finance agent you did not build?
  • We take the reference agent shipped with the Vals Finance Agent Benchmark v2, leave it untuned, and ask four questions a leaderboard score does not answer.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Rubric Rating

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: accuracy